Imaging genetics is an emerging and promising technique that investigates how genetic variations affect brain development, structure, and function. By exploiting disorder-related neuroimaging phenotypes, this class of studies provides a novel direction to reveal and understand the complex genetic mechanisms. Oftentimes, imaging genetics studies are challenging due to the relatively small number of subjects but extremely high-dimensionality of both imaging data and genomic data. In this dissertation, I carry on my research on imaging genetics with particular focuses on two tasks---building predictive models between neuroimaging data and genomic data, and identifying disorder-related genetic risk factors through image-based biomarkers. To this end, I consider a suite of structured sparse methods---that can produce interpretable models and are robust to overfitting---for imaging genetics. With carefully-designed sparse-inducing regularizers, different biological priors are incorporated into learning models. More specifically, in the Allen brain image--gene expression study, I adopt an advanced sparse coding approach for image feature extraction and employ a multi-task learning approach for multi-class annotation. Moreover, I propose a label structured-based two-stage learning framework, which utilizes the hierarchical structure among labels, for multi-label annotation. In the Alzheimer's disease neuroimaging initiative (ADNI) imaging genetics study, I employ Lasso together with EDPP (enhanced dual polytope projections) screening rules to fast identify Alzheimer's disease risk SNPs. I also adopt the tree-structured group Lasso with MLFre (multi-layer feature reduction) screening rules to incorporate linkage disequilibrium information into modeling. Moreover, I propose a novel absolute fused Lasso model for ADNI imaging genetics. This method utilizes SNP spatial structure and is robust to the choice of reference alleles of genotype coding. In addition, I propose a two-level structured sparse model that incorporates gene-level networks through a graph penalty into SNP-level model construction. Lastly, I explore a convolutional neural network approach for accurate predicting Alzheimer's disease related imaging phenotypes. Experimental results on real-world imaging genetics applications demonstrate the efficiency and effectiveness of the proposed structured sparse methods.

Buildings consume nearly 50% of the total energy in the United States, which drives the need to develop high-fidelity models for building energy systems. Extensive methods and techniques have been developed, studied, and applied to building energy simulation and forecasting, while most of work have focused on developing dedicated modeling approach for generic buildings. In this study, an integrated computationally efficient and high-fidelity building energy modeling framework is proposed, with the concentration on developing a generalized modeling approach for various types of buildings. First, a number of data-driven simulation models are reviewed and assessed on various types of computationally expensive simulation problems. Motivated by the conclusion that no model outperforms others if amortized over diverse problems, a meta-learning based recommendation system for data-driven simulation modeling is proposed. To test the feasibility of the proposed framework on the building energy system, an extended application of the recommendation system for short-term building energy forecasting is deployed on various buildings. Finally, Kalman filter-based data fusion technique is incorporated into the building recommendation system for on-line energy forecasting. Data fusion enables model calibration to update the state estimation in real-time, which filters out the noise and renders more accurate energy forecast. The framework is composed of two modules: off-line model recommendation module and on-line model calibration module. Specifically, the off-line model recommendation module includes 6 widely used data-driven simulation models, which are ranked by meta-learning recommendation system for off-line energy modeling on a given building scenario. Only a selective set of building physical and operational characteristic features is needed to complete the recommendation task. The on-line calibration module effectively addresses system uncertainties, where data fusion on off-line model is applied based on system identification and Kalman filtering methods. The developed data-driven modeling framework is validated on various genres of buildings, and the experimental results demonstrate desired performance on building energy forecasting in terms of accuracy and computational efficiency. The framework could be easily implemented into building energy model predictive control (MPC), demand response (DR) analysis and real-time operation decision support systems.

The presence of a rich set of embedded sensors on mobile devices has been fuelling various sensing applications regarding the activities of individuals and their surrounding environment, and these ubiquitous sensing-capable mobile devices are pushing the new paradigm of Mobile Crowd Sensing (MCS) from concept to reality. MCS aims to outsource sensing data collection to mobile users and it could revolutionize the traditional ways of sensing data collection and processing. In the meantime, cloud computing provides cloud-backed infrastructures for mobile devices to provision their capabilities with network access. With enormous computational and storage resources along with sufficient bandwidth, it functions as the hub to handle the sensing service requests from sensing service consumers and coordinate sensing task assignment among eligible mobile users to reach a desired quality of sensing service. This paper studies the problem of sensing task assignment to mobile device owners with specific spatio-temporal traits to minimize the cost and maximize the utility in MCS while adhering to QoS constraints. Greedy approaches and hybrid solutions combined with bee algorithms are explored to address the problem.

Moreover, the privacy concerns arise with the widespread deployment of MCS from both the data contributors and the sensing service consumers. The uploaded sensing data, especially those tagged with spatio-temporal information, will disclose the personal information of the data contributors. In addition, the sensing service requests can reveal the personal interests of service consumers. To address the privacy issues, this paper constructs a new framework named Privacy-Preserving Mobile Crowd Sensing (PP-MCS) to leverage the sensing capabilities of ubiquitous mobile devices and cloud infrastructures. PP-MCS has a distributed architecture without relying on trusted third parties for privacy-preservation. In PP-MCS, the sensing service consumers can retrieve data without revealing the real data contributors. Besides, the individual sensing records can be compared against the aggregation result while keeping the values of sensing records unknown, and the k-nearest neighbors could be approximately identified without privacy leaks. As such, the privacy of the data contributors and the sensing service consumers can be protected to the greatest extent possible.

Transfer learning refers to statistical machine learning methods that integrate the knowledge of one domain (source domain) and the data of another domain (target domain) in an appropriate way, in order to develop a model for the target domain that is better than a model using the data of the target domain alone. Transfer learning emerged because classic machine learning, when used to model different domains, has to take on one of two mechanical approaches. That is, it will either assume the data distributions of the different domains to be the same and thereby developing one model that fits all, or develop one model for each domain independently. Transfer learning, on the other hand, aims to mitigate the limitations of the two approaches by accounting for both the similarity and specificity of related domains. The objective of my dissertation research is to develop new transfer learning methods and demonstrate the utility of the methods in real-world applications. Specifically, in my methodological development, I focus on two different transfer learning scenarios: spatial transfer learning across different domains and temporal transfer learning along time in the same domain. Furthermore, I apply the proposed spatial transfer learning approach to modeling of degenerate biological systems.Degeneracy is a well-known characteristic, widely-existing in many biological systems, and contributes to the heterogeneity, complexity, and robustness of biological systems. In particular, I study the application of one degenerate biological system which is to use transcription factor (TF) binding sites to predict gene expression across multiple cell lines. Also, I apply the proposed temporal transfer learning approach to change detection of dynamic network data. Change detection is a classic research area in Statistical Process Control (SPC), but change detection in network data has been limited studied. I integrate the temporal transfer learning method called the Network State Space Model (NSSM) and SPC and formulate the problem of change detection from dynamic networks into a covariance monitoring problem. I demonstrate the performance of the NSSM in change detection of dynamic social networks.

Discriminative learning when training and test data belong to different distributions is a challenging and complex task. Often times we have very few or no labeled data from the test or target distribution, but we may have plenty of labeled data from one or multiple related sources with different distributions. Due to its capability of migrating knowledge from related domains, transfer learning has shown to be effective for cross-domain learning problems. In this dissertation, I carry out research along this direction with a particular focus on designing efficient and effective algorithms for BioImaging and Bilingual applications. Specifically, I propose deep transfer learning algorithms which combine transfer learning and deep learning to improve image annotation performance. Firstly, I propose to generate the deep features for the Drosophila embryo images via pretrained deep models and build linear classifiers on top of the deep features. Secondly, I propose to fine-tune the pretrained model with a small amount of labeled images. The time complexity and performance of deep transfer learning methodologies are investigated. Promising results have demonstrated the knowledge transfer ability of proposed deep transfer algorithms. Moreover, I propose a novel Robust Principal Component Analysis (RPCA) approach to process the noisy images in advance. In addition, I also present a two-stage re-weighting framework for general domain adaptation problems. The distribution of source domain is mapped towards the target domain in the first stage, and an adaptive learning model is proposed in the second stage to incorporate label information from the target domain if it is available. Then the proposed model is applied to tackle cross lingual spam detection problem at LinkedIn’s website. Our experimental results on real data demonstrate the efficiency and effectiveness of the proposed algorithms.

Recent advances in medical imaging technology have greatly enhanced imaging based diagnosis which requires computational effective and accurate algorithms to process the images (e.g., measure the objects) for quantitative assessment. In this dissertation, one type of imaging objects is of interest: small blobs. Example small blob objects are cells in histopathology images, small breast lesions in ultrasound images, glomeruli in kidney MR images etc. This problem is particularly challenging because the small blobs often have inhomogeneous intensity distribution and indistinct boundary against the background.

This research develops a generalized four-phased system for small blob detections. The system includes (1) raw image transformation, (2) Hessian pre-segmentation, (3) feature extraction and (4) unsupervised clustering for post-pruning. First, detecting blobs from 2D images is studied where a Hessian-based Laplacian of Gaussian (HLoG) detector is proposed. Using the scale space theory as foundation, the image is smoothed via LoG. Hessian analysis is then launched to identify the single optimal scale based on which a pre-segmentation is conducted. Novel Regional features are extracted from pre-segmented blob candidates and fed to Variational Bayesian Gaussian Mixture Models (VBGMM) for post pruning. Sixteen cell histology images and two hundred cell fluorescent images are tested to demonstrate the performances of HLoG. Next, as an extension, Hessian-based Difference of Gaussians (HDoG) is proposed which is capable to identify the small blobs from 3D images. Specifically, kidney glomeruli segmentation from 3D MRI (6 rats, 3 humans) is investigated. The experimental results show that HDoG has the potential to automatically detect glomeruli, enabling new measurements of renal microstructures and pathology in preclinical and clinical studies. Realizing the computation time is a key factor impacting the clinical adoption, the last phase of this research is to investigate the data reduction technique for VBGMM in HDoG to handle large-scale datasets. A new coreset algorithm is developed for variational Bayesian mixture models. Using the same MRI dataset, it is observed that the four-phased system with coreset-VBGMM has similar performance as using the full dataset but about 20 times faster.

Sparse learning is a powerful tool to generate models of high-dimensional data with high interpretability, and it has many important applications in areas such as bioinformatics, medical image processing, and computer vision. Recently, the a priori structural information has been shown to be powerful for improving the performance of sparse learning models. A graph is a fundamental way to represent structural information of features. This dissertation focuses on graph-based sparse learning. The first part of this dissertation aims to integrate a graph into sparse learning to improve the performance. Specifically, the problem of feature grouping and selection over a given undirected graph is considered. Three models are proposed along with efficient solvers to achieve simultaneous feature grouping and selection, enhancing estimation accuracy. One major challenge is that it is still computationally challenging to solve large scale graph-based sparse learning problems. An efficient, scalable, and parallel algorithm for one widely used graph-based sparse learning approach, called anisotropic total variation regularization is therefore proposed, by explicitly exploring the structure of a graph. The second part of this dissertation focuses on uncovering the graph structure from the data. Two issues in graphical modeling are considered. One is the joint estimation of multiple graphical models using a fused lasso penalty and the other is the estimation of hierarchical graphical models. The key technical contribution is to establish the necessary and sufficient condition for the graphs to be decomposable. Based on this key property, a simple screening rule is presented, which reduces the size of the optimization problem, dramatically reducing the computational cost.

Data imbalance and data noise often coexist in real world datasets. Data imbalance affects the learning classifier by degrading the recognition power of the classifier on the minority class, while data noise affects the learning classifier by providing inaccurate information and thus misleads the classifier. Because of these differences, data imbalance and data noise have been treated separately in the data mining field. Yet, such approach ignores the mutual effects and as a result may lead to new problems. A desirable solution is to tackle these two issues jointly. Noting the complementary nature of generative and discriminative models, this research proposes a unified model fusion based framework to handle the imbalanced classification with noisy dataset.

The phase I study focuses on the imbalanced classification problem. A generative classifier, Gaussian Mixture Model (GMM) is studied which can learn the distribution of the imbalance data to improve the discrimination power on imbalanced classes. By fusing this knowledge into cost SVM (cSVM), a CSG method is proposed. Experimental results show the effectiveness of CSG in dealing with imbalanced classification problems.

The phase II study expands the research scope to include the noisy dataset into the imbalanced classification problem. A model fusion based framework, K Nearest Gaussian (KNG) is proposed. KNG employs a generative modeling method, GMM, to model the training data as Gaussian mixtures and form adjustable confidence regions which are less sensitive to data imbalance and noise. Motivated by the K-nearest neighbor algorithm, the neighboring Gaussians are used to classify the testing instances. Experimental results show KNG method greatly outperforms traditional classification methods in dealing with imbalanced classification problems with noisy dataset.

The phase III study addresses the issues of feature selection and parameter tuning of KNG algorithm. To further improve the performance of KNG algorithm, a Particle Swarm Optimization based method (PSO-KNG) is proposed. PSO-KNG formulates model parameters and data features into the same particle vector and thus can search the best feature and parameter combination jointly. The experimental results show that PSO can greatly improve the performance of KNG with better accuracy and much lower computational cost.

Network traffic analysis by means of Quality of Service (QoS) is a popular research and development area among researchers for a long time. It is becoming even more relevant recently due to ever increasing use of the Internet and other public and private communication networks. Fast and precise QoS analysis is a vital task in mission-critical communication networks (MCCNs), where providing a certain level of QoS is essential for national security, safety or economic vitality. In this thesis, the details of all aspects of a comprehensive computational framework for QoS analysis in MCCNs are provided. There are three main QoS analysis tasks in MCCNs; QoS measurement, QoS visualization and QoS prediction. Definitions of these tasks are provided and for each of those, complete solutions are suggested either by referring to an existing work or providing novel methods.

A scalable and accurate passive one-way QoS measurement algorithm is proposed. It is shown that accurate QoS measurements are possible using network flow data.

Requirements of a good QoS visualization platform are listed. Implementations of the capabilities of a complete visualization platform are presented.

Steps of QoS prediction task in MCCNs are defined. The details of feature selection, class balancing through sampling and assessing classification algorithms for this task are outlined. Moreover, a novel tree based logistic regression method for knowledge discovery is introduced. Developed prediction framework is capable of making very accurate packet level QoS predictions and giving valuable insights to network administrators.

In a healthcare setting, the Sterile Processing Department (SPD) provides ancillary services to the Operating Room (OR), Emergency Room, Labor & Delivery, and off-site clinics. SPD's function is to reprocess reusable surgical instruments and return them to their home departments. The management of surgical instruments and medical devices can impact patient safety and hospital revenue. Any time instrumentation or devices are not available or are not fit for use, patient safety and revenue can be negatively impacted. One step of the instrument reprocessing cycle is sterilization. Steam sterilization is the sterilization method used for the majority of surgical instruments and is preferred to immediate use steam sterilization (IUSS) because terminally sterilized items can be stored until needed. IUSS Items must be used promptly and cannot be stored for later use. IUSS is intended for emergency situations and not as regular course of action. Unfortunately, IUSS is used to compensate for inadequate inventory levels, scheduling conflicts, and miscommunications. If IUSS is viewed as an adverse event, then monitoring IUSS incidences can help healthcare organizations meet patient safety goals and financial goals along with aiding in process improvement efforts. This work recommends statistical process control methods to IUSS incidents and illustrates the use of control charts for IUSS occurrences through a case study and analysis of the control charts for data from a health care provider. Furthermore, this work considers the application of data mining methods to IUSS occurrences and presents a representative example of data mining to the IUSS occurrences. This extends the application of statistical process control and data mining in healthcare applications.